Sowing machine operation soil compaction detection and evaluation method

Abstract

The invention discloses a sower operation soil compaction detection and evaluation method, and relates to the field of agriculture. The invention aims to solve the problem that soil is damaged due to soil compaction in the operation process of the seeder. The invention relates to a sower operation soil compaction detection and evaluation method. The method comprises the following steps: collecting characteristic data of a sower and carrying out standardization processing; calculating the soil compaction degree by utilizing the characteristic data of the sowing machine after standardization treatment; calculating a risk index according to the soil compaction degree; and calculating a comprehensive score according to the risk index, and realizing early warning according to the comprehensive score.

Description

Technical Field

[0001] The invention belongs to the field of agriculture. Background Art

[0002] The extensive use of agricultural machinery has improved the modernization of agricultural production, reduced the labor burden for agricultural production, and improved production efficiency. During the operation of wheeled agricultural machinery, due to the small contact area between the tire and the ground, the overloaded driving of agricultural machinery and the heavy deadweight of large agricultural machinery, the deep soil layer will be compacted during the operation.

[0003] Soil compaction will increase the density of the soil and significantly reduce the gaps between the soil, which will make it difficult for precipitation to quickly penetrate into the soil, and will easily cause obvious surface runoff, causing soil erosion. In addition, the number and activity of beneficial microorganisms in the soil will be significantly reduced, affecting the decomposition rate of nutrients in the soil and causing soil quality to deteriorate. In addition, soil compaction will increase the hardness of the soil, increase the resistance to crop root growth, reduce the absorption of crop nutrients, and cause crop yield reduction.

[0004] However, current technology has not yet been able to achieve real-time early warning of soil compaction in black soil, resulting in increasingly serious soil compaction problems. Summary of the invention

[0005] The invention aims to solve the problem that soil compaction during the operation of a seeder may cause damage to the soil, and now provides a method for detecting and evaluating soil compaction during the operation of a seeder.

[0006] A soil compaction detection method for a seeder operation, comprising:

[0007] The planter characteristic data is collected and standardized, wherein the planter characteristic data includes: the planter's own weight, the number of steering wheel rotations, the number of manual gear shifting times and the acceleration change rate, and the soil compaction degree is calculated using the standardized planter characteristic data.

[0008] Furthermore, the above-mentioned soil compaction detection method for seed drill operation also includes: calculating a risk index according to the soil compaction degree.

[0009] Furthermore, the expression of the above standardization process is:

[0010] X′= X-μ ,

[0011] σ

[0012] Among them, X and X′ are the characteristic data before and after standardization, μ is the mean of the characteristic data, and σ is the standard deviation of the characteristic data.

[0013] Furthermore, the soil compaction degree is calculated using the standardized seed drill characteristic data, including:

[0014] The calculation model of soil compaction is:

[0015]

[0016] Among them, C is the soil compaction degree, W′ is the standardized deadweight of the planter, T′ is the standardized number of steering wheel rotations, G′ is the standardized number of manual gear shifting, A′ is the standardized rate of change of acceleration, β0 is the intercept term, β1, β2, β3, and β4 are the linear term weights of W′, T′, G′, and A′, respectively, and β5, β6, β7, and β8 are the linear term weights of W′, T′, G′, and A′, respectively. 2 , T′ 2 , G′ 2 , A′ 2 The square term weight, β9 is the interaction term weight between W′ and T′, β 10 is the interaction weight between W′ and G′, β 11 is the interaction weight between W′ and A′, β 12 is the interaction weight between T′ and G′, β 13 is the interaction weight between T′ and A′, β 14 is the interaction weight between G′ and A′.

[0017] Furthermore, the above weight coefficient β i The values ​​are:

[0018] β0=2.0, β1=0.6, β2=0.3, β3=0.2, β4=0.2, β5=0.02, β6=0.01, β7=0.05,

[0019] β8=0.01、β9=0.05、β 10 =0.04, β 11 =0.03, β 12 =0.03, β 13 =0.02, β 14 =0.02.

[0020] Furthermore, the above-mentioned calculation of the risk index according to the soil compaction degree includes:

[0021] The risk index is calculated using a piecewise function, and the piecewise function expression is:

[0022]

[0023] Among them, R is the risk index, C is the soil compaction degree, α is the growth rate of controlling medium risk; β is the initial value of medium and high risk; γ is the growth rate of controlling medium and high risk; δ is the initial value of high risk; η is the growth rate of controlling high risk.

[0024] Furthermore, the parameter values ​​of the above piecewise function are:

[0025] α=50, β=50, γ=80, δ=100, η=150.

[0026] A soil compaction assessment method for seed drill operation, which calculates a comprehensive score based on a risk index, includes:

[0027] Build a weighted scoring model:

[0028] S=ω(α1W′+α2T′+α3G′+α4A′+λR),

[0029] Among them, S is the comprehensive score, ω is the amplification factor, α1, α2, α3, and α4 are the weight coefficients of W′, T′, G′, and A′ respectively, W′ is the standardized deadweight of the planter, T′ is the standardized number of steering wheel rotations, G′ is the standardized number of manual gear shifting, A′ is the standardized acceleration change rate, and λ is the weight coefficient of the risk index R;

[0030] The weight coefficient of the weighted scoring model is optimized using a genetic algorithm to obtain an optimized model:

[0031]

[0032] in, λ * These are the results after optimization of α1, α2, α3, α4, and λ respectively;

[0033] The optimized model is used to calculate and obtain a comprehensive score.

[0034] Furthermore, the objective function J(·) of the above weighted scoring model is:

[0035]

[0036] Where N = 4 is the total number of samples, n = 1, 2, ..., N, S n pred Score the model predictions, S n true Score actual observations;

[0037] The constraints of the objective function are:

[0038] α1+α2+α3+α4+λ=1,

[0039] α n ≥0,λ≥0.

[0040] Furthermore, an early warning is issued according to the following rules:

[0041] When S≤25, a green warning is issued;

[0042] When 25<S≤50, a yellow warning is issued;

[0043] When 50<S≤75, an orange warning is issued;

[0044] When 75<S≤100, a red warning is issued.

[0045] The soil compaction detection and evaluation method for seed drill operation described in the present invention can obtain soil compaction information without installing sensors in the soil through analysis and calculation of real-time monitoring data, and then dynamically evaluate the compaction risk level, and provide compaction warnings based on different levels, which reflects strong real-time performance. At the same time, the present invention provides important data support for subsequent agricultural research such as field path optimization planning of seed drills and soil remediation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The present invention is a flow chart of a method for detecting and evaluating soil compaction during seed drill operation. DETAILED DESCRIPTION

[0047] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0048] Specific implementation method 1: refer to Figure 1 Specifically describing this embodiment, a soil compaction detection method for a seeder operation described in this embodiment specifically includes:

[0049] 1. Calculation of soil compaction

[0050] Real-time monitoring of planter characteristic data, including:

[0051] The deadweight of the seeder W is monitored in real time by a pressure sensor installed on the chassis of the seeder;

[0052] The number of steering wheel rotations T is recorded in real time by a rotary encoder installed on the steering wheel;

[0053] The number of manual gear shifting times G is measured by installing a contact sensor at the gear shifting position of the manual transmission. When the gear position changes, it records the number of gear shifting times in real time.

[0054] The acceleration change rate A is obtained in real time through the acceleration sensor installed on the planter's vehicle-mounted equipment.

[0055] The real-time monitored seeder data is standardized to obtain standardized characteristic data: standardized seeder deadweight W′, standardized steering wheel rotation times T′, standardized manual gear shifting times G′, and standardized acceleration change rate A′.

[0056] The expression of the standardization process is:

[0057]

[0058] Among them, X and X′ are the characteristic data before and after standardization, μ is the mean of the characteristic data, and σ is the standard deviation of the characteristic data.

[0059] The standardized feature data are input into the polynomial regression prediction model of soil compaction C based on the seeder feature data, and the soil compaction C is output.

[0060] The polynomial regression prediction model expression is:

[0061]

[0062] Among them, β i is the weight coefficient, i=0,1,2,...,14, the specific values ​​are as follows:

[0063] β0 is the intercept term, and its value is β0=2.0;

[0064] β1, β2, β3, and β4 are the linear term weights of W′, T′, G′, and A′, respectively, and the values ​​are β1 = 0.6, β2 = 0.3, β3 = 0.2, and β4 = 0.2;

[0065] β5, β6, β7 and β8 are respectively W′ 2 , T′ 2 , G′ 2 , A′ 2 The square weights of are β5=0.02, β6=0.01, β7=0.05, and β8=0.01;

[0066] β9 is the interaction weight between W′ and T′, β 10 is the interaction weight between W′ and G′, β 11 is the interaction weight between W′ and A′, β12 is the interaction weight between T′ and G′, β 13 is the interaction weight between T′ and A′, β 14 is the interaction weight between G′ and A′, with values ​​of β9=0.05, β 10 =0.04, β 11 =0.03, β 12 =0.03, β 13 =0.02, β 14 =0.02.

[0067] In this implementation, the polynomial regression prediction model expression is:

[0068]

[0069] 2. Risk Index Calculation

[0070] Piecewise function:

[0071]

[0072] Among them, R is the risk index, and there is a nonlinear relationship between R and C. The risk index increases slowly when the soil compaction degree is low, and the risk index rises sharply when the soil compaction degree is high.

[0073] α is the growth rate of controlling medium risk, which is 50; β is the initial value of medium-high risk, which is 50; γ is the growth rate of controlling medium-high risk, which is 80; δ is the initial value of high risk, which is 100; η is the growth rate of controlling high risk, which is 150.

[0074] C≤1.5 means that no additional measures are needed; 1.5<C≤2.0 means that the exponent increases with the compaction degree as a square function; 2.0<C≤2.5 means that the exponent increases with the compaction degree as a square function, and an initial value is superimposed; C>2.5 means that the exponent increases with the compaction degree as a cubic function, and an initial value is superimposed.

[0075] Substituting the above parameters into the piecewise function, we have:

[0076]

[0077] The output soil compaction degree C is input into the piecewise function according to the piecewise rule, and the risk index R is output.

[0078] 3. Risk level classification:

[0079] R=0, low risk, green warning;

[0080] 50≤R<100, medium risk, yellow warning;

[0081] 100≤R<200, medium-high risk, orange warning;

[0082] R≥200, high risk, red warning.

[0083] Specific implementation method 2: refer to Figure 1 Specifically describing this embodiment, a soil compaction assessment method for a seeder operation described in this embodiment specifically includes:

[0084] Construct a weighted scoring model:

[0085] S=ω(α1W′+α2T′+α3G′+α4A′+λR),

[0086] Among them, S is the comprehensive score; ω is the amplification factor, which is 9.13; α1, α2, α3, and α4 are the weight coefficients of the seeder’s own weight, the number of steering wheel turns, the number of manual gear shifting, and the acceleration change rate of the tractor and seeder, respectively, with values ​​of α1=0.3, α2=0.25, α3=0.2, and α4=0.15; λ is the weight coefficient of the risk index R, which is 0.1.

[0087] Construct the objective function:

[0088]

[0089] Where N = 4 is the total number of samples, n = 1, 2, ..., N, S n pred Score the model predictions, S n true Score actual observations.

[0090] The constraints of the objective function are:

[0091] α1+α2+α3+α4+λ=1,

[0092] α n ≥0,λ≥0.

[0093] The weighted scoring model is optimized using a genetic algorithm to obtain an optimized model:

[0094]

[0095] λ * They are the results of optimization of α1, α2, α3, α4, and λ, and their values ​​are: λ * =0.05.

[0096] The optimized model in this implementation is actually:

[0097] S=9.13(0.35W′+0.25T′+0.2G′+0.15A′+0.05R).

[0098] After obtaining the comprehensive score S as described above, the warning level is divided according to the following rules:

[0099] S≤25, green warning, the buzzer does not sound an alarm;

[0100] 25<S≤50, yellow warning, the buzzer emits intervals and weak sounds;

[0101] 50<S≤75, orange warning, the buzzer emits a sound with decreasing interval and increasing volume;

[0102] 75<S≤100, red warning, the buzzer emits a very small interval and very loud sound.

[0103] In summary, the present invention proposes a soil compaction polynomial regression prediction model based on seed drill data, and combines it with a soil compaction risk assessment model to construct a comprehensive early warning method. The system optimizes the weight coefficient by introducing a genetic algorithm to achieve weighted scoring, and evaluates the degree of soil compaction by the seed drill in real time based on the scoring results. Finally, the system issues timely warnings to operators through visual and auditory warnings, helping to effectively control the risk of soil compaction.

[0104] Although the present invention is described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the present invention. It should therefore be understood that many modifications may be made to the exemplary embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the various dependent claims and features described herein may be combined in a manner different from that described in the original claims. It should also be understood that the features described in conjunction with a single embodiment may be used in other described embodiments.

Claims

1. A method for detecting soil compaction during seeding operation, characterized in that: include: The planter characteristic data is collected and standardized, wherein the planter characteristic data includes: the planter's own weight, the number of steering wheel rotations, the number of manual gear shifting times and the acceleration change rate, and the soil compaction degree is calculated using the standardized planter characteristic data.

2. A soil compaction detection method for seed drill operation according to claim 1, characterized in that: Also includes: A risk index is calculated based on the soil compaction degree.

3. A soil compaction detection method for seed drill operation according to claim 1 or 2, characterized in that: The expression of the standardization process is: Among them, X and X′ are the characteristic data before and after standardization, μ is the mean of the characteristic data, and σ is the standard deviation of the characteristic data.

4. A soil compaction detection method for seed drill operation according to claim 1 or 2, characterized in that: The method of calculating soil compaction degree using the standardized seed drill characteristic data includes: The calculation model of soil compaction is: Among them, C is the soil compaction degree, W′ is the standardized deadweight of the planter, T′ is the standardized number of steering wheel rotations, G′ is the standardized number of manual gear shifting, A′ is the standardized rate of change of acceleration, β0 is the intercept term, β1, β2, β3, and β4 are the linear term weights of W′, T′, G′, and A′, respectively, and β5, β6, β7, and β8 are the linear term weights of W′, T′, G′, and A′, respectively. 2 , T′ 2 , G′ 2 , A′ 2 The square term weight, β9 is the interaction term weight between W′ and T′, β 10 is the interaction weight between W′ and G′, β 11 is the interaction weight between W′ and A′, β 12 is the interaction weight between T′ and G′, β 13 is the interaction weight between T′ and A′, β 14 is the interaction weight between G′ and A′.

5. A soil compaction detection method for seed drill operation according to claim 4, characterized in that: Weight coefficient β i The values ​​are: β0＝2.0、β1＝0.6、β2＝0.3、β3＝0.2、β4＝0.2、β5＝0.02、β6＝0.01、β7＝0.05、 β8＝0.01、β9＝0.05、β 10 ＝0.04、β 11 ＝0.03、β 12 ＝0.03、β 13 ＝0.02、β 14 ＝0.02。 6. A soil compaction detection method for seed drill operation according to claim 2, characterized in that: Calculating the risk index according to the soil compaction degree includes: The risk index is calculated using a piecewise function, and the piecewise function expression is: Among them, R is the risk index, C is the soil compaction degree, α is the growth rate of controlling medium risk; β is the initial value of medium and high risk; γ is the growth rate of controlling medium and high risk; δ is the initial value of high risk; η is the growth rate of controlling high risk.

7. A soil compaction detection method for seed drill operation according to claim 6, characterized in that: The parameter values ​​of the piecewise function are: α=50, β=50, γ=80, δ=100, η=150.

8. A method for evaluating soil compaction during seed drill operation, characterized in that: A comprehensive score is calculated based on the risk index, including: Build a weighted scoring model: S=ω(α1W′+α2T′+α3G′+α4A′+λR), Among them, S is the comprehensive score, ω is the amplification factor, α1, α2, α3, and α4 are the weight coefficients of W′, T′, G′, and A′ respectively, W′ is the standardized deadweight of the planter, T′ is the standardized number of steering wheel rotations, G′ is the standardized number of manual gear shifting, A′ is the standardized acceleration change rate, and λ is the weight coefficient of the risk index R; The weight coefficient of the weighted scoring model is optimized using a genetic algorithm to obtain an optimized model: in, λ * These are the results after optimization of α1, α2, α3, α4, and λ respectively; The optimized model is used to calculate and obtain a comprehensive score.

9. A soil compaction assessment method for seed drill operation according to claim 8, characterized in that: The objective function J(·) of the weighted scoring model is: Where N = 4 is the total number of samples, n = 1, 2, ..., N, S n pred Score the model predictions, S n true Score actual observations; The constraints of the objective function are: α1+α2+α3+α4+λ=1, a n ≥0,λ≥0.

10. A soil compaction assessment method for seed drill operation according to claim 8 or 9, characterized in that: Warnings are issued according to the following rules: When S≤25, a green warning is issued; When 25<S≤50, a yellow warning is issued; When 50<S≤75, an orange warning is issued; When 75<S≤100, a red warning is issued.

Images